Increased MRI-based brain age in chronic migraine patients

Neuroimaging has revealed that migraine is linked to alterations in both the structure and function of the brain. However, the re-lationship of these changes with aging has not been studied in detail. Here we employ the Brain Age framework to analyze migraine, by building a machine learning model that predicts age from neuroimaging data. We hypothesize that migraine pa-tients will exhibit an increased Brain Age Gap (the difference between the predicted age and the chronological age) compared to healthy participants. We trained a machine learning model to predict Brain Age from 2,771 T1-weighted magnetic resonance imaging scans of healthy subjects. The processing pipeline in-cluded the automatic segmentation of the images, the extraction of 1,479 imaging features (both morphological and intensity-based), harmonization, feature selection and training inside a 10-fold cross-validation scheme. Separate models based only on morphological and intensity features were also trained, and all the Brain Age models were later applied to a discovery cohort composed of 247 subjects, divided into healthy controls (HC, n=82), episodic migraine (EM, n=91), and chronic migraine pa-tients (CM, n=74). CM patients showed an increased Brain Age Gap compared to HC (4.16 vs -0.56 years, P=0.01). A smaller Brain Age Gap was found for EM patients, not reaching sta-tistical significance (1.21 vs -0.56 years, P=0.19). No associa-tions were found between the Brain Age Gap and headache or migraine frequency, or duration of the disease. Brain imag-ing features that have previously been associated with migraine were among the main drivers of the differences in the predicted age. Also, the separate analysis using only morphological or intensity-based features revealed different patterns in the Brain Age biomarker in patients with migraine. The brain-predicted age has shown to be a sensitive biomarker of CM patients and can help reveal distinct aging patterns in migraine.